Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss
applied to the outputs of a neural network, when the softmax is used. But, what guarantees …

The study on improving the robustness of deep neural networks against adversarial
examples grows rapidly in recent years. Among them, adversarial training is the most …

Adversarial training, in which a network is trained on adversarial examples, is one of the few
defenses against adversarial attacks that withstands strong attacks. Unfortunately, the high …

Mode connectivity provides novel geometric insights on analyzing loss landscapes and
enables building high-accuracy pathways between well-trained neural networks. In this …

Deep neural networks are vulnerable to adversarial attacks which can fool them by adding
minuscule perturbations to the input images. The robustness of existing defenses suffers …

Adversarial training (AT) has become the de-facto standard to obtain models robust against
adversarial examples. However, AT exhibits severe robust overfitting: cross-entropy loss on …

Deep-learning models have demonstrated remarkable performance in a variety of fields,
owing to advancements in computational power and the availability of extensive datasets for …

Deep neural networks can easily be fooled by an adversary with minuscule perturbations
added to an input image. The existing defense techniques suffer greatly under white-box …

Recent works have shown that self-supervised learning can achieve remarkable robustness
when integrated with adversarial training (AT). However, the robustness gap between …

Recent studies have shown that the generalization ability of deep neural networks (DNNs) is
closely related to the Fisher information matrix (FIM) calculated during the early training …